Merge tag 'kvm-arm-for-4.3' of git://git.kernel.org/pub/scm/linux/ker…

…nel/git/kvmarm/kvmarm into kvm-queue

KVM/ARM changes for 4.3

- Full debug support for arm64
- Active state switching for timer interrupts
- Lazy FP/SIMD save/restore for arm64
- Generic ARMv8 target

Documentation/virtual/kvm/api.txt

@@ -2671,7 +2671,7 @@ handled.
 4.87 KVM_SET_GUEST_DEBUG
 
 Capability: KVM_CAP_SET_GUEST_DEBUG
-Architectures: x86, s390, ppc
+Architectures: x86, s390, ppc, arm64
 Type: vcpu ioctl
 Parameters: struct kvm_guest_debug (in)
 Returns: 0 on success; -1 on error
@@ -2693,8 +2693,8 @@ when running. Common control bits are:
 The top 16 bits of the control field are architecture specific control
 flags which can include the following:
 
-  - KVM_GUESTDBG_USE_SW_BP:     using software breakpoints [x86]
-  - KVM_GUESTDBG_USE_HW_BP:     using hardware breakpoints [x86, s390]
+  - KVM_GUESTDBG_USE_SW_BP:     using software breakpoints [x86, arm64]
+  - KVM_GUESTDBG_USE_HW_BP:     using hardware breakpoints [x86, s390, arm64]
   - KVM_GUESTDBG_INJECT_DB:     inject DB type exception [x86]
   - KVM_GUESTDBG_INJECT_BP:     inject BP type exception [x86]
   - KVM_GUESTDBG_EXIT_PENDING:  trigger an immediate guest exit [s390]
@@ -2709,6 +2709,11 @@ updated to the correct (supplied) values.
 The second part of the structure is architecture specific and
 typically contains a set of debug registers.
 
+For arm64 the number of debug registers is implementation defined and
+can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
+KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
+indicating the number of supported registers.
+
 When debug events exit the main run loop with the reason
 KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
 structure containing architecture specific debug information.
@@ -3111,11 +3116,13 @@ data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
 KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
+		/* KVM_EXIT_DEBUG */
 		struct {
 			struct kvm_debug_exit_arch arch;
 		} debug;
 
-Unused.
+If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
+for which architecture specific information is returned.
 
 		/* KVM_EXIT_MMIO */
 		struct {

arch/arm/include/asm/kvm_host.h

@@ -231,4 +231,9 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
+static inline void kvm_arm_init_debug(void) {}
+static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/kvm/arm.c

@@ -125,6 +125,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_free_stage2_pgd;
 
+	kvm_vgic_early_init(kvm);
 	kvm_timer_init(kvm);
 
 	/* Mark the initial VMID generation invalid */
@@ -249,6 +250,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
+	kvm_vgic_vcpu_early_init(vcpu);
 }
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
@@ -278,6 +280,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
 
+	kvm_arm_reset_debug_ptr(vcpu);
+
 	return 0;
 }
 
@@ -301,13 +305,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_arm_set_running_vcpu(NULL);
 }
 
-int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-					struct kvm_guest_debug *dbg)
-{
-	return -EINVAL;
-}
-
-
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
@@ -528,10 +525,20 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (vcpu->arch.pause)
 			vcpu_pause(vcpu);
 
-		kvm_vgic_flush_hwstate(vcpu);
+		/*
+		 * Disarming the background timer must be done in a
+		 * preemptible context, as this call may sleep.
+		 */
 		kvm_timer_flush_hwstate(vcpu);
 
+		/*
+		 * Preparing the interrupts to be injected also
+		 * involves poking the GIC, which must be done in a
+		 * non-preemptible context.
+		 */
 		preempt_disable();
+		kvm_vgic_flush_hwstate(vcpu);
+
 		local_irq_disable();
 
 		/*
@@ -544,12 +551,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
 			local_irq_enable();
+			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
 			kvm_timer_sync_hwstate(vcpu);
-			kvm_vgic_sync_hwstate(vcpu);
 			continue;
 		}
 
+		kvm_arm_setup_debug(vcpu);
+
 		/**************************************************************
 		 * Enter the guest
 		 */
@@ -564,6 +573,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Back from guest
 		 *************************************************************/
 
+		kvm_arm_clear_debug(vcpu);
+
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
@@ -586,11 +597,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 */
 		kvm_guest_exit();
 		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
-		preempt_enable();
 
+		kvm_vgic_sync_hwstate(vcpu);
+
+		preempt_enable();
 
 		kvm_timer_sync_hwstate(vcpu);
-		kvm_vgic_sync_hwstate(vcpu);
 
 		ret = handle_exit(vcpu, run, ret);
 	}
@@ -921,6 +933,8 @@ static void cpu_init_hyp_mode(void *dummy)
 	vector_ptr = (unsigned long)__kvm_hyp_vector;
 
 	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+
+	kvm_arm_init_debug();
 }
 
 static int hyp_init_cpu_notify(struct notifier_block *self,

arch/arm/kvm/guest.c

@@ -290,3 +290,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 {
 	return -EINVAL;
 }
+
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
+{
+	return -EINVAL;
+}

arch/arm/kvm/interrupts.S

@@ -361,10 +361,6 @@ hyp_hvc:
 	@ Check syndrome register
 	mrc	p15, 4, r1, c5, c2, 0	@ HSR
 	lsr	r0, r1, #HSR_EC_SHIFT
-#ifdef CONFIG_VFPv3
-	cmp	r0, #HSR_EC_CP_0_13
-	beq	switch_to_guest_vfp
-#endif
 	cmp	r0, #HSR_EC_HVC
 	bne	guest_trap		@ Not HVC instr.
 
@@ -378,7 +374,10 @@ hyp_hvc:
 	cmp     r2, #0
 	bne	guest_trap		@ Guest called HVC
 
-host_switch_to_hyp:
+	/*
+	 * Getting here means host called HVC, we shift parameters and branch
+	 * to Hyp function.
+	 */
 	pop	{r0, r1, r2}
 
 	/* Check for __hyp_get_vectors */
@@ -409,6 +408,10 @@ guest_trap:
 
 	@ Check if we need the fault information
 	lsr	r1, r1, #HSR_EC_SHIFT
+#ifdef CONFIG_VFPv3
+	cmp	r1, #HSR_EC_CP_0_13
+	beq	switch_to_guest_vfp
+#endif
 	cmp	r1, #HSR_EC_IABT
 	mrceq	p15, 4, r2, c6, c0, 2	@ HIFAR
 	beq	2f
@@ -477,7 +480,6 @@ guest_trap:
  */
 #ifdef CONFIG_VFPv3
 switch_to_guest_vfp:
-	load_vcpu			@ Load VCPU pointer to r0
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.

arch/arm/kvm/reset.c

@@ -77,7 +77,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	kvm_reset_coprocs(vcpu);
 
 	/* Reset arch_timer context */
-	kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
-
-	return 0;
+	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
 }

arch/arm64/include/asm/hw_breakpoint.h

@@ -16,6 +16,8 @@
 #ifndef __ASM_HW_BREAKPOINT_H
 #define __ASM_HW_BREAKPOINT_H
 
+#include <asm/cputype.h>
+
 #ifdef __KERNEL__
 
 struct arch_hw_breakpoint_ctrl {
@@ -132,5 +134,17 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task)
 
 extern struct pmu perf_ops_bp;
 
+/* Determine number of BRP registers available. */
+static inline int get_num_brps(void)
+{
+	return ((read_cpuid(ID_AA64DFR0_EL1) >> 12) & 0xf) + 1;
+}
+
+/* Determine number of WRP registers available. */
+static inline int get_num_wrps(void)
+{
+	return ((read_cpuid(ID_AA64DFR0_EL1) >> 20) & 0xf) + 1;
+}
+
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_BREAKPOINT_H */

arch/arm64/include/asm/kvm_arm.h

@@ -171,10 +171,13 @@
 #define HSTR_EL2_TTEE	(1 << 16)
 #define HSTR_EL2_T(x)	(1 << x)
 
+/* Hyp Coproccessor Trap Register Shifts */
+#define CPTR_EL2_TFP_SHIFT 10
+
 /* Hyp Coprocessor Trap Register */
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
-#define CPTR_EL2_TFP	(1 << 10)
+#define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TDRA		(1 << 11)

arch/arm64/include/asm/kvm_asm.h

@@ -46,24 +46,16 @@
 #define	CNTKCTL_EL1	20	/* Timer Control Register (EL1) */
 #define	PAR_EL1		21	/* Physical Address Register */
 #define MDSCR_EL1	22	/* Monitor Debug System Control Register */
-#define DBGBCR0_EL1	23	/* Debug Breakpoint Control Registers (0-15) */
-#define DBGBCR15_EL1	38
-#define DBGBVR0_EL1	39	/* Debug Breakpoint Value Registers (0-15) */
-#define DBGBVR15_EL1	54
-#define DBGWCR0_EL1	55	/* Debug Watchpoint Control Registers (0-15) */
-#define DBGWCR15_EL1	70
-#define DBGWVR0_EL1	71	/* Debug Watchpoint Value Registers (0-15) */
-#define DBGWVR15_EL1	86
-#define MDCCINT_EL1	87	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+#define MDCCINT_EL1	23	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 
 /* 32bit specific registers. Keep them at the end of the range */
-#define	DACR32_EL2	88	/* Domain Access Control Register */
-#define	IFSR32_EL2	89	/* Instruction Fault Status Register */
-#define	FPEXC32_EL2	90	/* Floating-Point Exception Control Register */
-#define	DBGVCR32_EL2	91	/* Debug Vector Catch Register */
-#define	TEECR32_EL1	92	/* ThumbEE Configuration Register */
-#define	TEEHBR32_EL1	93	/* ThumbEE Handler Base Register */
-#define	NR_SYS_REGS	94
+#define	DACR32_EL2	24	/* Domain Access Control Register */
+#define	IFSR32_EL2	25	/* Instruction Fault Status Register */
+#define	FPEXC32_EL2	26	/* Floating-Point Exception Control Register */
+#define	DBGVCR32_EL2	27	/* Debug Vector Catch Register */
+#define	TEECR32_EL1	28	/* ThumbEE Configuration Register */
+#define	TEEHBR32_EL1	29	/* ThumbEE Handler Base Register */
+#define	NR_SYS_REGS	30
 
 /* 32bit mapping */
 #define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
@@ -132,6 +124,8 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
 
+extern u32 __kvm_get_mdcr_el2(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -103,15 +103,34 @@ struct kvm_vcpu_arch {
 
 	/* HYP configuration */
 	u64 hcr_el2;
+	u32 mdcr_el2;
 
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
-	/* Debug state */
+	/* Guest debug state */
 	u64 debug_flags;
 
+	/*
+	 * We maintain more than a single set of debug registers to support
+	 * debugging the guest from the host and to maintain separate host and
+	 * guest state during world switches. vcpu_debug_state are the debug
+	 * registers of the vcpu as the guest sees them.  host_debug_state are
+	 * the host registers which are saved and restored during
+	 * world switches. external_debug_state contains the debug
+	 * values we want to debug the guest. This is set via the
+	 * KVM_SET_GUEST_DEBUG ioctl.
+	 *
+	 * debug_ptr points to the set of debug registers that should be loaded
+	 * onto the hardware when running the guest.
+	 */
+	struct kvm_guest_debug_arch *debug_ptr;
+	struct kvm_guest_debug_arch vcpu_debug_state;
+	struct kvm_guest_debug_arch external_debug_state;
+
 	/* Pointer to host CPU context */
 	kvm_cpu_context_t *host_cpu_context;
+	struct kvm_guest_debug_arch host_debug_state;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
@@ -122,6 +141,17 @@ struct kvm_vcpu_arch {
 	 * here.
 	 */
 
+	/*
+	 * Guest registers we preserve during guest debugging.
+	 *
+	 * These shadow registers are updated by the kvm_handle_sys_reg
+	 * trap handler if the guest accesses or updates them while we
+	 * are using guest debug.
+	 */
+	struct {
+		u32	mdscr_el1;
+	} guest_debug_preserved;
+
 	/* Don't run the guest */
 	bool pause;
 
@@ -216,15 +246,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 		     hyp_stack_ptr, vector_ptr);
 }
 
-struct vgic_sr_vectors {
-	void	*save_vgic;
-	void	*restore_vgic;
-};
-
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
+void kvm_arm_init_debug(void);
+void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
+void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
+void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */